Deep Learning of Activation Energies

Grambow, Colin A.; Pattanaik, Lagnajit; Green, William

doi:10.1021/acs.jpclett.0c00500

Cited by 155 publications

(214 citation statements)

References 34 publications

Supporting

Mentioning

211

Contrasting

Order By: Relevance

“…[64][65][66] Although promising, we believe that widespread use of hybrid models is currently held back by difficulties in computing transition states in an effective and reliable way. We envision that this problem will be solved in the near future by deep learning approaches that can predict both TS geometries 67 and DFT-computed barriers 27 based on large, publicly available datasets. 68,69 In the end, machine learning for reaction prediction needs to reproduce experiment, and transfer learning will probably be key to utilizing small high-quality kinetic datasets together with large amounts of computationally generated data.…”

Section: Chemical Science Accepted Manuscriptmentioning

confidence: 99%

Machine learning meets mechanistic modelling for accurate prediction of experimental activation energies

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Chemical Science Accepted Manuscriptmentioning

confidence: 99%

Machine learning meets mechanistic modelling for accurate prediction of experimental activation energies

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[55][56][57] Although promising, we believe that widespread use of hybrid models is currently held back by difficulties in computing transition states in an effective and reliable way. We envision that this problem will be solved in the near future by deep learning approaches that can predict both TS geometries 58 and DFT-computed barriers 26 based on large, publicly available datasets. 59,60 In the end, machine learning for reaction prediction needs to reproduce experiment, and transfer learning will probably be key to utilizing small high-quality kinetic datasets together with large amounts of computationally generated data.…”

Section: Discussionmentioning

confidence: 99%

“…Here, transfer learning might ultimately represent the best of both worlds. Models pre-trained on a very large number of DFT-calculated barriers 26 can be retrained on a much smaller amount of high-quality experimental data to achieve chemical accuracy for a wide range of reaction classes.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Meets Mechanistic Modelling for Accurate Prediction of Experimental Activation Energies

Jorner

Brinck²,

Norrby³

et al. 2020

Preprint

View full text Add to dashboard Cite

Accurate prediction of chemical reactions in solution is challenging for current state-of-the-art approaches based on transition state modelling with density functional theory. Models based on machine learning have emerged as a promising alternative to address these problems, but these models currently lack the precision to give crucial information on the magnitude of barrier heights, influence of solvents and catalysts and extent of regio- and chemoselectivity. Here, we construct hybrid models which combine the traditional transition state modelling and machine learning to accurately predict reaction barriers. We train a Gaussian Process Regression model to reproduce high-quality experimental kinetic data for the nucleophilic aromatic substitution reaction and use it to predict barriers with a mean absolute error of 0.77 kcal/mol for an external test set. The model was further validated on regio- and chemoselectivity prediction on patent reaction data and achieved a competitive top-1 accuracy of 86%, despite not being trained explicitly for this task. Importantly, the model gives error bars for its predictions that can be used for risk assessment by the end user. Hybrid models emerge as the preferred alternative for accurate reaction prediction in the very common low-data situation where only 100–150 rate constants are available for a reaction class. With recent advances in deep learning for quickly predicting barriers and transition state geometries from density functional theory, we envision that hybrid models will soon become a standard alternative to complement current machine learning approaches based on ground-state physical organic descriptors or structural information such as molecular graphs or fingerprints.

show abstract

“…There have also been significant advances in methods for computing solvation effects 36,37 . There have also been continuing improvements in methods for estimating rate and thermochemistry parameters (including solvation and pressure‐dependence of rate coefficients) 38‐44 and in algorithms for solving kinetic simulations 45‐53 . We suggest an efficient workflow combining all these software components to build predictive models in Figure 1.…”

Section: Technical Issuesmentioning

confidence: 99%